deterministic-replay repositories

Trending repositories tagged deterministic-replay, ranked by trending score. Updated daily.

  1. 1
    OpenAdaptAI/OpenAdapt

    For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.

    GitHub · Python · 1,890 stars · 285 forks · +5 stars in 24 hours · Trending score 1.70

  2. 2
    sipyourdrink-ltd/bernstein

    Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

    GitHub · Python · 1,216 stars · 185 forks · +3 stars in 24 hours · Trending score 1.27

  3. 3
    Quchaosheng/workbench-mobile-home-robot

    Evidence-first runtime for a wheeled mobile household robot with bounded actions, replayable events, and fail-closed verification.

    GitHub · Python · 264 stars · 8 forks · 0 stars in 24 hours · Trending score 0.31

  4. 4
    Dicklesworthstone/franken_engine

    Native Rust runtime for adversarial JavaScript/TypeScript extension workloads: native-only core execution (no V8/JSC/QuickJS), deterministic replay of high-impact decisions, and Ed25519-signed evidence for every containment action. Research-grade; automation ships advisory-only.

    GitHub · Rust · 35 stars · 4 forks · 0 stars in 24 hours · Trending score 0.22

  5. 5
    kostyk348/rlisp-engine

    Игровой движок, где игра — это Lisp-файл, а Rust — только HAL: растр, ввод, звук, PNG, HTTP. Без зависимостей, hot reload, детерминированный replay, ~1.2 МБ WASM.

    GitHub · Rust · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08

  6. 6
    easy1ive/famulix

    Offline memory-first personal-agent framework with a deterministic daily briefing app: provenance-tracked memory graph, consolidation and decay, budgeted hybrid retrieval, preference calibration, privacy tiers, plan DSL, byte-deterministic replay, synthetic personas. NumPy core, optional CPU-only torch extra.

    GitHub · Python · 31 stars · 238 forks · 0 stars in 24 hours · Trending score 0.07

  7. 7
    OpenAdaptAI/openadapt-flow

    Now part of OpenAdapt: https://github.com/OpenAdaptAI/OpenAdapt (packages/flow)

    GitHub · Python · 10 stars · 4 forks · 0 stars in 24 hours · Trending score 0.01

  8. 8
    Miko997/metriplane

    Open-source physical observability for robotics workcells: deterministic replay, verifiable incident evidence, and generated regression tests.

    GitHub · Python · 41 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    NekomyaDev/nudge

    A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

    GitHub · Rust · 20 stars · 13 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    DITlieD/ELAI-archive

    Local-first, model-agnostic LLM agent-harness research. Restart planned after a hiatus; existing code and historical claims await revalidation. MIT.

    GitHub · Rust · 24 stars · 9 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    hraness/algal

    ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve through evaluation.

    GitHub · TypeScript · 21 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    zhiyongmm/diurnix

    Offline personal-agent runtime + life apps: seeded persona factory with planted ground truth, tool registry, policy engine with PII redaction, plan DSL, budgeted act loop, approval flows, byte-deterministic replay, tiered memory, inbox/calendar triage, task planning, ledger anomaly detection, habit streaks. NumPy core, CPU-only torch extra.

    GitHub · Python · 23 stars · 251 forks · 0 stars in 24 hours · Trending score 0.00